Figure 1
![11: The ECG, PCG (low and high filtered), carotid pulse, apex cardiogram, and logic states (high-open) of left heart valves, mitral and aortic valve, right heart valves, and tricuspid and pulmonary valve. Left heart mechanical intervals are indicated by vertical lines: isovolumetric contraction (1), ejection (2), isovolumetric relaxation (3), and filling (4) (rapid filling, slow filling, atrial contraction). The low-frequency PCG shows the four normal heart sounds (I, II, III, and IV). In the high-frequency trace, III and IV have disappeared and splitting is visible in I [Ia and Ib (and even a small Ic due to ejection)] and in II [IIA (aortic valve) and IIP (pulmonary valve)]. Systolic intervals LVEP (on carotid curve) and Q-IIA (on ECG and PCG) are indicated.](profile/Abbas_K_Abbas/publication/210290203/figure/fig10/AS:643179598585863@1530357374302/The-ECG-PCG-low-and-high-filtered-carotid-pulse-apex-cardiogram-and-logic-states.png)
11: The ECG, PCG (low and high filtered), carotid pulse, apex cardiogram, and logic states (high-open) of left heart valves, mitral and aortic valve, right heart valves, and tricuspid and pulmonary valve. Left heart mechanical intervals are indicated by vertical lines: isovolumetric contraction (1), ejection (2), isovolumetric relaxation (3), and filling (4) (rapid filling, slow filling, atrial contraction). The low-frequency PCG shows the four normal heart sounds (I, II, III, and IV). In the high-frequency trace, III and IV have disappeared and splitting is visible in I [Ia and Ib (and even a small Ic due to ejection)] and in II [IIA (aortic valve) and IIP (pulmonary valve)]. Systolic intervals LVEP (on carotid curve) and Q-IIA (on ECG and PCG) are indicated.
Source publication
* Auscultation method is an important diagnostic indicator for hemodynamic anomalies. Heart sounds classification and analysis play an important role in the primary diagnosis phase for many cardiomyopathy diseases .
The term phonocardiography refers to the tracing technique of heart sounds and the recording of cardiac acoustics vibration by means...
Citations
... Usually, a typical time duration and low-frequency spectral content characterize each FHS. For instance, the s 1 components dominate the region from 10 Hz to 140 Hz, while the s 2 components usually concentrate their energy around the 10 Hz to 200 Hz band [2] . ...
... The database described at the beginning of this sec- [2] . ...
... We analyzed the influence of signal quality in the algorithm performance. According to the noise condition labels mentioned in the low-quality recordings subsection, we evaluated the signals tagged as HQR (2,874) and LQR (279) separately. The oversampling and under-sampling balancing procedures were also considered. ...
Cardiovascular diseases (CVDs) remain the leading cause of morbidity worldwide. The heart sound signal or phonocardiogram (PCG) is the most simple, low-cost, and effective tool to assist physicians in diagnosing CVDs. Advances in signal processing and machine learning have motivated the design of computer-aided systems for heart illness detection based only on the PCG. The objective of this work is to compare the effects of using spectral and sparse features for a classification scheme to detect the presence/absence of a pathological state in a heart sound signal, more specifically, sparse representations using Matching Pursuit with multiscale Gabor time-frequency dictionaries, linear prediction coding, and Mel-frequency cepstral coefficients. This work compares the performance of PCGs classification applying features as a result of averaging the samples or the features for each PCG sound event when feeding a random forest (RF) classifier. For data balancing, random under-sampling and synthetic minority oversampling (SMOTE) methods were applied. Furthermore, we compare the Correlation Feature Selection (CFS) and Information Gain (IG) for the dimensionality reduction. The findings show a SE=93.17 %, SP=84.32 % and ACC=85.9 % when joining MP+LPC+MFCC features set with an AUC=0.969 showing that these features are promising to be used in heart sounds anomaly detection schemes.
... Stress, diabetes, obesity, high blood cholesterol, smoking, absence of exercise, and hypertension, which are conditions that largely depend on lifestyle, can cause heart diseases, heart valve diseases, and heart failure [2,4,5]. Heart valve diseases are usually detected functionally and/or anatomically using various detection techniques [2,4], such as stethoscopes, Cardiac-CT, US Echocardiograph, Cardiac-MRI, ECG, and cardiac catheterization [2]. ...
... Stress, diabetes, obesity, high blood cholesterol, smoking, absence of exercise, and hypertension, which are conditions that largely depend on lifestyle, can cause heart diseases, heart valve diseases, and heart failure [2,4,5]. Heart valve diseases are usually detected functionally and/or anatomically using various detection techniques [2,4], such as stethoscopes, Cardiac-CT, US Echocardiograph, Cardiac-MRI, ECG, and cardiac catheterization [2]. ...
... The sounds created by various cardiac structures as the blood is pumped and move through them are detected, where phonocardiogram (PCG) record is commonly used as the graphical representation of the recorded heart sounds and murmurs. The blood's acceleration and deceleration as well as the turbulence caused by the rapid blood flow are what produce the sound [4,[7][8][9]. Fig. 1 shows a sample of recorded PCG. ...
According to recent reports by the world health organization (WHO), heart valve disease is one of the leading causes of death around the world. Due to the complex anatomy of the heart, it is quite challenging task to develop a system for heart sound localization, and therefore, there is a need for an accurate axial heart sound localization and tomography imaging for detecting heart valve disease. The proposed approach of Axial heart sound tomography aims to improve the accuracy and speed of heart-valves disease diagnostics. We have developed a simulation hybrid system of a chest shape microphone array with a CT image at the same chest level for functional heart sound tomography imaging that has been proposed , analyzed and computationally evaluated. In the proposed method, the heart valve sound distribution responses are collected simultaneously from the array of surrounding microphones. To increase the response array resolution, an upsampling, using bicubic interpolation, is performed to provide, mathematically , a higher sound localization resolution in the process of axial heart sound tomographic image reconstruction. The sound localization simulation of two different scenarios are considered, first for aortic and pulmonary valves and second for bicuspid and tricuspid valves. The results show that the proposed approach can reconstruct a heart-valves sound image with a resolution of 15.32 mm and 11.9 mm in x-and y-directions respectively. The proposed simulation hybrid system shows its ability to accurately localize the heart valves with high resolution in both  and y directions. Thus, the proposed method provides a useful analytical and diagnostic tool for heart valves by estimating their sound-based problems.
... The Canny operator edge-extraction results are shown in Figure 7c. (2) Image thresholding method with edge-contour extraction The use of image segmentation to separate the target region from the background region can prevent the need to conduct a blind search on the image and greatly improve the processing efficiency of the image [24,25]. Threshold segmentation based on the grayscale histogram is simple to compute and is suitable for grayscale images where the target and background are distributed in different grayscale ranges, as shown in Figure 7 for the histogram of the original image. ...
... The use of image segmentation to separate the target region from the background region can prevent the need to conduct a blind search on the image and greatly improve the processing efficiency of the image [24,25]. Threshold segmentation based on the grayscale histogram is simple to compute and is suitable for grayscale images where the target and background are distributed in different grayscale ranges, as shown in Figure 7 for the histogram of the original image. ...
The quantitative measurement of finger-joint range of motion plays an important role in assessing the level of hand disability and intervening in the treatment of patients. An industrial monocular-vision-based knuckle-joint-activity-measurement system is proposed with short measurement time and the simultaneous measurement of multiple joints. In terms of hardware, the system can adjust the light-irradiation angle and the light-irradiation intensity of the marker by actively adjusting the height of the light source to enhance the difference between the marker and the background and reduce the difficulty of segmenting the target marker and the background. In terms of algorithms, a combination of multiple-vision algorithms is used to compare the image-threshold segmentation and Hough outer- and inner linear detection as the knuckle-activity-range detection method of the system. To verify the accuracy of the visual-detection method, nine healthy volunteers were recruited for experimental validation, and the experimental results showed that the average angular deviation in the flexion/extension of the knuckle was 0.43° at the minimum and 0.59° at the maximum, and the average angular deviation in the adduction/abduction of the knuckle was 0.30° at the minimum and 0.81° at the maximum, which were all less than 1°. In the multi-angle velocimetry experiment, the time taken by the system was much less than that taken by the conventional method.
... A detailed review and state-f-the-art techniques of HS processing and classification are discussed in [20][21][22]. The abnormal characteristics of the HS signal were stated in [23], while the different signal processing techniques involved in the HS signal analysis are discussed in [24]. In [25], recent works related to feature selection and classification were discussed. ...
Machine Learning (ML) can be defined as the method of studying and analyzing data to build a computerized analytical model. Machine learning is a branch of Artificial Intelligence which works on data learnt from it and without explicit programming, it identifies the major problem and with minimal human interference makes the final decisions. In the past era we have come across various applications of machine learning for instance in self-driven cars, speech recognition systems and various web search related filter applications. It has highly contributed in better understanding of the human genome. ML technology being so persistent is used almost a dozen of time in a day without actually knowing it. Recent developments in the field of ML had led to a major breakthrough in this technology that eases the process of collecting, analyzing and interpreting the unprecedented et al. 98 amount of sensor related data. In the current scenario where modern "Smart Sensors" are emerging, that have changed the conventional understanding of the system of sensors. The modern-day smart sensor comprises of machine learning algorithms and it also uses modern day hardware called "Smart Models" that are well organized specifically for smart sensor-based applications and it also includes the smart tailored sensing technologies for a more sophisticated application of the sensing technology. In this chapter we will discuss the following: emerging sensing applications, which includes the use of both smart sensors and machine learning technology, the most common and the first known smart sensor system used in practical sensing, two broad categories of practical sensing technology-physical and chemical sensing techniques and visual image sensing applications to elaborate the use of ML based "Smart Sensor Models." Lastly, the challenges in this area would also be highlighted involving the outlook on the present trajectory and proposed solutions that will be used in future by smart sensing systems and future opportunities in this area will also be covered.
... e phonocardiogram signal [1] contains important information about the heart's operations and is used to detect various heart disorders [2]. However, recording PCG signals and other biomedical signals [3,4] is very challenging since they are susceptible to environmental noise apart from the other noise signals [5]. ...
... e best estimate of the clean signal is achieved at stage 3. In Figure 6, the output of the proposed filter is compared with the conventional Sign Error LMS filter and the existing 2-stage [49] and 3-stage [50] cascaded adaptive filter (1) Stage I ANC primary input signal � d 1 (n) � s(n) + v(n) (2) Stage I adaptive filter reference input signal � x 1 (n) � v′(n) (3) Step-size parameter μ 1SELMS � μ 1LMS /10 for stage I Sign Error LMS adaptive filter (4) Filter order � M (5) Iterations � N (6) ρ threshold ; k (7) Outputs (8) Stages (L), Error (e), Filter outputs (y), Weights (w) (9) Execution (10) Compute μ max 1 � 2/λ max 1 (11) Compute the parameters for stage I ANC using SELMS adaptive algorithm. ...
Phonocardiogram (PCG), the graphic recording of heart signals, is analyzed to determine the cardiac mechanical function. In the recording of PCG signals, the major problem encountered is the corruption by surrounding noise signals. The noise-corrupted signal cannot be analyzed and used for advanced processing. Therefore, there is a need to denoise these signals before being employed for further processing. Adaptive Noise Cancellers are best suited for signal denoising applications and can efficiently recover the corrupted PCG signal. This paper introduces an optimal adaptive filter structure using a Sign Error LMS algorithm to estimate a noise-free signal with high accuracy. In the proposed filter structure, a noisy signal is passed through a multistage cascaded adaptive filter structure. The number of stages to be cascaded and the step size for each stage are adjusted automatically. The proposed Variable Stage Cascaded Sign Error LMS (SELMS) adaptive filter model is tested for denoising the fetal PCG signal taken from the SUFHS database and corrupted by Gaussian and colored pink noise signals of different input SNR levels. The proposed filter model is also tested for pathological PCG signals in the presence of Gaussian noise. The simulation results prove that the proposed filter model performs remarkably well and provides 8–10 dB higher SNR values in a Gaussian noise environment and 2-3 dB higher SNR values in the presence of colored noise than the existing cascaded LMS filter models. The MSE values are improved by 75–80% in the case of Gaussian noise. Further, the correlation between the clean signal and its estimate after denoising is more than 0.99. The PSNR values are improved by 7 dB in a Gaussian noise environment and 1-2 dB in the presence of pink noise. The advantage of using the SELMS adaptive filter in the proposed filter model is that it offers a cost-effective hardware implementation of Adaptive Noise Canceller with high accuracy.
... This suggests that breaking the heart vibration signals into two different groups based on the respiration cycle information can result in a better signal characterization [19]. Other popular signal processing and analysis methods of the cardiovascular-induced sound and vibration signals have been reviewed in previous work [5,6,[24][25][26]. ...
In the past few decades, many non-invasive monitoring methods have been developed based on body acoustics to investigate a wide range of medical conditions, including cardiovascular diseases, respiratory problems, nervous system disorders, and gastrointestinal tract diseases. Recent advances in sensing technologies and computational resources have given a further boost to the interest in the development of acoustic-based diagnostic solutions. In these methods, the acoustic signals are usually recorded by acoustic sensors, such as microphones and accelerometers, and are analyzed using various signal processing, machine learning, and computational methods. This paper reviews the advances in these areas to shed light on the state-of-the-art, evaluate the major challenges, and discuss future directions. This review suggests that rigorous data analysis and physiological understandings can eventually convert these acoustic-based research investigations into novel health monitoring and point-of-care solutions.
... Electronic stethoscopes are widely used to detect heart sounds. PCG is a signal recording that occurs as a result of recording sound vibrations using different techniques [8]. Time, frequency, periodicity, and sound quality analysis of heart sounds can be performed with PCG. ...
Background
Heart valve diseases are commonly seen ailments, and many people suffer from these diseases. Therefore, early diagnosis and accurate treatment are crucial for these disorders. This research aims to diagnose heart valve diseases automatically by employing a new stable feature generation method.
Materials and method
This research presents a stable feature generator-based automated heart diseases diagnosis model. This model uses three primary sections. They are stable feature generation using the improved one-dimensional binary pattern (IBP), selecting the most discriminative feature with neighborhood component analysis (NCA), and classification employing the conventional classifiers. IBP uses three kernels, and they are named signum, left signed, and right signed kernels. By applying these kernels, 768 features are generated. NCA aims to choose the most discriminative ones, and 64 features are chosen to employ NCA. The k nearest neighbor (kNN) and support vector machine (SVM) classifier are employed in the classification phase. Open access (public published) Phonocardiogram signal (PCG) sound dataset is used to calculate this model's measurements. This dataset contains 1000 PCGs with five categories.
Results
The presented IBP and NCA-based heart valve disorders classification model tested using kNN and SVM classifier and attained 99.5% and 98.30% accuracies, respectively.
Conclusions
Per the results, the presented IBP and NCA-based PCG sound classification is a successful method. Moreover, this model is basic and high accurate. Therefore, it is ready for the development of real-time implementations.
... These sounds are results of vibrations caused by the closure of heart valves. [3] Based on collected information about numbers of people with heart disease and deaths caused by it, this is noticeably the area of human life which requires to be improved when it comes to the faster and more reliable heart disease detection. ...
Heart diseases are the number one cause of death all over the world. Many deaths are caused due to late detection of heart diseases. During the process of heart sound recording, beside heart sound, environment noise is being recorded too. In this work signal denoising was performed using wavelet denoising method. Furthermore, parameter values are compared to find the best combination. Signal to noise ratio (SNR), mean square error (MSE), root mean square error (RMSE) and peak signal to noise ratio (PSNR) were calculated to evaluate results. The highest mean value of the signal-to-noise ratio was 85.38 and it is obtained by Daubechies wavelet method with order 16, ‘sqwtolog’ threshold selection rule and threshold rescaling ‘one’. Wavelet denoising is appropriate method for phonocardiogram analysis and could be useful in heart disease detection.
... Phonocardiogram (PCG) is a graphically recorded heart sound signal which provides valuable diagnostic information related to the performance of heart valves. Hence it is widely used as a non-invasive diagnostic tool to detect heart diseases [1] [2]. Electronic Stethoscopes are used to acquire the PCG signal, but being a very weak amplitude signal, it is highly susceptible to noise and motion artifacts [3]. ...
Phonocardiogram (PCG) signal contains significant bio-acoustic information reflecting the operation of the heart, and is used to detect the various diseases related to heart valve. But it is highly susceptible to noise, and the sources of noise includes lung and breath sounds, noise from contact between the recording device and skin, environmental noise, etc. Hence, denoising of PCG signal is very important for the proper diagnosis of heart diseases. In this paper, a discrete wavelet transform (DWT) based threshold tuning is investigated to deliver denoised PCG signal. The performance of the denoising algorithm is evaluated using different metrics such as mean-square error, normalized-mean-square error, root-mean-square error, percentage root-mean-square difference, and signal-to-noise ratio by determining the most suitable parameters (wavelet family, level of decomposition, and thresholding type) for the denoising process. The evaluation results obtained from the different metrics gives the best denoising performance from the reconstructed PCG signal.
... The heart makes some mechanical movements through the closing of cardiac valves during each heartbeat; those are the source of the vibrations in the myocardial wall that are translated into sounds known as heart sounds or phonocardiogram "PCG" [3] [4]. ...
em>The heart is the organ that pumps blood with oxygen and nutrients into all body organs by a rhythmic cycle overlapping between contraction and dilatation. This is done by producing an audible sound which we can hear using a stethoscope. Many are the causes affecting the normal function of this most vital organ. In this respect, the heart sound classification has become one of the diagnostic tools that allow the discrimination between patients and healthy people; this diagnosis is less painful, less costly and less time consuming. In this paper, we present a classification algorithm based on the extraction of 20 features from segmented phonocardiogram “PCG” signals. We applied four types of machine learning classifiers that are k- Near Neighbor “KNN”, Support Vector Machine “SVM”, Tree, and Naïve Bayes “NB” so as to train old features and predict the new entry. To make our results measurable, we have chosen the PASCAL Classifying Heart Sounds challenge, which is a rich database and is conducive to classifying the PCGs into four classes for dataset A and three classes for dataset B. The main finding is about 3.06 total precision of the dataset A and 2.37 of the dataset B.</em
